UNIT 5 (EXPERT SYSTEM)

What is Expert systems?

Expert systems are a crucial subset of artificial intelligence (AI) that simulate the
decision-making ability of a human expert. These systems use a knowledge base
filled with domain-specific information and rules to interpret and solve complex
problems. Expert systems are widely used in fields such as medical diagnosis,
accounting, coding, and even in games.

Block diagram of Expert System

Examples of expert systems:

 CaDet (Cancer Decision Support Tool) is used to identify cancer in its
earliest stages.
 DENDRAL helps chemists identify unknown organic molecules.
 Dxplain is a clinical support system that diagnoses various diseases
 MYCIN identifies bacteria such as bacteremia and meningitis, and
recommends antibiotics and dosages.
 PXDES determines the type and severity of lung cancer a person has
 RI/XCON is an early manufacturing expert system that automatically
selects and orders computer components based on customer specifications

Characteristics of Expert System:

  High Performance: The expert system provides high performance for
solving any type of complex problem of a specific domain with high
efficiency and accuracy.
 Understandable: It responds in a way that can be easily understandable by
the user. It can take input in human language and provides the outputs in
the same way.
 Reliable: It is much reliable for generating an efficient and accurate output
 Highly responsive: ES provides the result for any complex query within a
very short period of time

Componenets of Expert System:

An Expert System mainly consists of three Components
 User Interface
 Inference Engine
 Knowledge Base

>User Interface
 With the help of a user interface, the expert system interacts with the user,
takes queries as an input in a readable format, and Passes it to the inference
engine.
 After getting the response from the inference engine, it displays the output
to the user. In other words, it is an interface that helps a non-expert user to
communicate with the expert system to find a solution
>Inference Engine
 The inference engine is known as the brain of the expert system as it is the
main Processing unit of the system. It applies inference rules to the
knowledge base to derive a conclusion or deduce new information.
 With the help of an Inference engine, the system extracts the knowledge
from the Knowledge base.
 Two types of inference Engine

1. Deterministic inference engine:

The conclusions drawn from this type of inference engine are assumed to be true.
It is based on facts and rules
2. Probabilistic Inference engine:
This type of inference engine contains uncertainity in conclusions, and based on
the probability.

>Knowledge Base
 The Knowledge base is a type of storage that stores knowledge acquired
from the different experts of the particular domain. It is considered as big
storage of knowledge.
 It is similar to a database that contains information and rules of a particular
domain or subject.
 One can also view the knowledge base as Collections of objects and their
attributes. Such as a lion is an object and its attributes are it is a mammal,
it is not a domestic animal.

Capabilities of the Expert System

 Advising: It is capable of advising the human being for the query of any
domain from the particular ES
 Provide decision-making Capabilities: It provides the capability of
decision making in any domain, such as for making any financial decision,
decisions in medical science, etc.,
 Demonstrate a device: It is capable of demonstrating any new Products
such as its features, specifications, how to use that product, etc.,
 Problem-solving: It has problem-solving, capabilities
  Explaining a problem: It is also capable of providing a detailed
description of an input problem
 Interpreting the input: It is capable of interpreting the input given by the
user.

Advantages of Expert System

 These systems are highly reproducible.
 They can be used for risky places where the human presence is not safe.
 Error possibilities are less if the KB contains correct Knowledge.
 The performance of these systems remains steady as it is not affected by
emotions, tension, or fatigue.
 They provide a very high speed to respond to a particular query.

Limitations of Expert System

 The response of the ES may get wrong if the knowledge base contains the
wrong Information.
 Like a human being, it cannot produce a creative output for different
scenarios.
 Its maintenance and development cost, are very high.
 Knowledge acquisition for designing is much difficult.
 for each domain, we require a specific ES, which is one of the big
limitations.
 It cannot learn from itself and hence requires manual updates.

Applications of Expert System

 Designing and manufacturing domain: It can be broadly used for
designing and manufacturing physical devices such as camera Lenses and
automobiles.
 Knowledge Domain: These systems are primarily used for publishing the
relevant knowledge to the users. The two popular ES used for this domain
is an advisor and a tax advisor.
 Finance Domain: In the finance industries, it is used to detect any type of
possible fraud, suspicious activity, and advise bankers that if they should
provide loans for business or not
  Planning and scheduling: The expert systems can also be used for
Planning and scheduling some particular tasks for achieving the goal of
that task.

Types of Expert Systems:

 Rule-Based Expert Systems.
 Frame-Based Expert Systems.
 Fuzzy Logic Systems.
 Neural Network -Based Expert Systems.
 Neuro-Fuzzy Expert Systems.

1. Rule-Based Expert Systems:

Use a set of "if-then" rules to process data and make decisions. These rules are
typically written by human experts and capture domain-specific knowledge.
Example: MYCIN, an early system for diagnosing bacterial infections.
2. Frame-Based Expert Systems:
Represent knowledge using frames, which are data structures similar to objects
in Programming. Each frame contains attributes and values related to a particular
concept.
Example: Systems used for knowledge Representation in areas Like NLP
3. Fuzzy Logic Systems:
It Handle uncertain or imprecise information using fuzzy logic, which allows for
Partial truths rather than binary true false Values.
Examples. Fuzzy control systems for managing household appliances Like
washing machines and air conditioners.
4. Neural Network-Based Expert Systems:
It use Artificial neural networks to learn from data and make predictions or
decisions based on learned patterns. They are often used for tasks involving
pattern recognition and classification.
Example. Deep Learning models for image and speech recognition.
5. Neuro-Fuzzy Expert Systems:
Neural networks and fuzzy logic to combine the learning capabilities of neural
networks with the handling of uncertainity and imprecision offered by fuzzy
logic.
This hybrid approach helps in dealing with complex problems where both pattern
recognition and uncertain reasoning are required.
Example: Automated control systems that adjust based on uncertain
environmental conditions or financial forecasting models that handle both
quantitative data and fuzzy inputs.

How Expert Systems Work?

 Input Data: Users provide data or queries related to a specific problem or
scenario.
 Processing: The inference engine processes the input data using the rules
in the knowledge base to generate conclusions or recommendations.
 Output: The system presents the results or solutions to the user through the
user interface.
Explanation: If applicable, the system explains how the conclusions were
reached, providing Insights into the reasoning process.

Fundamental Methods of Expert System

 Forward chaining
 Backward chaining

1. Forward chaining:
 "What can happen next?" The inference engine follows the chain of
conditions and derivations and finally deduces the outcome.
 It considers all the facts and rules, and sorts them before concluding to a
solution
 This strategy is followed for working on conclusion, result, or effect.
  Example, prediction of share market status as an effect of changes in
interest rates.

2. Backward chaining:
 An expert system finds out the answer to the question, "Why this
happened?"
 On the basis of what has already happened, the inference Engine tries to
find out which conditions could have happened in the past for this result.
 This strategy is followed for finding out cause or reason.
 Example: diagnosis of blood cancer in humans

COMMON SENSE
 Common sense is the mental skills that most people share.
 Common Sense is ability to analyze a situation based on its context, using
millions of integrated pieces of common knowledge.
  Common sense is what people come to know in the process of growing and
living in the world.
 Common sense knowledge includes the basic facts about events and their
effects, facts about knowledge and how it is obtained, facts about beliefs
and desires. It includes the basic facts about material objects and their
properties
 Example: Everyone knows that dropping a glass of water, the glass will
break and water will spill on podium. However, this information is not
Obtained by formula or equation for a falling body or equations governing
fluid flow.
 The goal of the formal common sense reasoning community is to encode
this implicit knowledge using format logic Common sense is Identified as:

>) Common sense knowledge: What every one know

>) Common sense reasoning: ability to use common sense knowledge

Common sense knowledge:

What one can express as a fact using a richer ontology
Example:
1. Every person is younger than the Person's mother
2. If you hold a knife by it's blade then the blade may cut you.
3. If you drop paper into a flame then the paper will burn.

Common sense Reasoning:

What one builds as a reasoning method into his program.
Example:
1. If you have a problem, think of a past situation where you solved a similar
problem
2. If you fall at something, imagine how you might have done things
differently.
Common sense Architecture:
 The system takes as input a template Produced by information extraction
system about certain aspects of a scenario
  The template is a frame with slots and slots fillers
 The template is fed to a script classifier, which classifies what script is
active in the template
 The template and the script are passed to a reasoning problem builder
specific to the script, which converts the template into a commonsense
reasoning problem.
 The problem and a commonsense knowledge base are passed to a
commonsense reasoner. It infers and fills in missing details to Produce a
model of the input text.
 The model provides a deeper representation of the input, than is provided
by the template alone.

Importance of Common Sense in Expert System

 Improved decision-making
 Enhanced problem-solving
 Increased accuracy
 Better understanding of human behavior
 More natural human-computer interaction

Challenges of Implementing Common Sense

 Knowledge Acquisition
 Representation and organization
 Integration with domain - specific knowledge
 Reasoning and inference
 Evaluation and validation

Techniques for Implementing Common Sense

 Knowledge graph-based approaches
 Machine learning and deep Learning
 Natural Language Processing and understanding
 Cognitive architectures and modeling
 Hybrid approaches

Applications of common Sense

  Natural language Processing & generation
 Computer vision and image understanding.
 Robotics and autonomous systems
 Expert systems and decision support
 Human-computer interaction & dialogue systems

Qualitative physics
 Qualitative physics in AI is a way to study the physical world by
representing and reasoning about it.
 Qualitative physics uses dimensional analysis to solve problems, which
requires Knowledge of physical variables and dimensional representation.
 This allows reasoning about systems and devices without needing to know
the physical laws that govern them.
 for eg:, if a problem involves time period, mass, and spring constant, the
variables and their dimensions are t (T), m [M], K[MT-2].
 Qualitative Physics can also be used to solve physical system problems,
and can be used for tasks like behavior analysis and conceptual design.

Techniques used in Qualitative physics

 Qualitative simulation: Simulating physical phenomena using qualitative
models, such as qualitative differential equations
 Model-based reasoning: Using qualitative models to reason about physical
systems and predict behaviors.
 Case-based reasoning: Storing and retrieving cases Physical phenomena to
reason about new situations
 Ontologies: Representing physical knowledge using ontologies, which
provide a framework for organizing and reasoning about qualitative
knowledge
Applications of Qualitative Physics
 Robotics: Enables robots to understand and interact with their physical
environment
 Computer vision: Allows for qualitative understanding of visual scenes and
events
 Natural Language Processing: Enables understanding of physical
phenomena described in Natural language.
  Expert Systems: Provides a foundation for building expert systems that
reason about physical domains.

Benefits of Qualitative Physics

 Improved explainability: Provides insights into Physical phenomena and
system behaviors.
 Robustness. Less sensitive to numerical errors and uncertainties
 Flexibility: Can handle incomplete or uncertain knowledge
 Efficiency: Reduces computational complexity in certain applications

COMMON SENSE ONTOLOGIST

 An Ontologist is a professional who specializes in designing, developing,
and managing ontologies.
 The primary goal is to create a structured and comprehensive
representation of Knowledge that can be easily understood and utilized by
both humans and machines.
 Ontologies are used to facilitate Knowledge sharing, communication,
collaboration between humans and machines.

How ontologies used in AI?

In AI, ontologies are used to model Knowledge about the world in a structured
form. This allows AI systems to understand and reason about the relationships
between concepts, improving their ability to process natural language, make
decisions, and learn from data

Applications of Ontologists in AI
 Expert Systems: Ontologists in AI develop Ontologies that power expert
systems, which mimic human decision-making in a particular domain
 Natural Language Processing: Ontologists in AI use ontologies to improve
natural language processing systems, enabling machines to understand
human language
 Decision Support Systems: It support decision-making in complex
domains
  Data Integration: Ontologists in AI use ontologies to integrate data from
multiple sources, enabling machines to reason about the integrated data.
 Robotics and autonomous system: It enable robots and autonomous
systems to understand their environment and make decisions

Key Components of Ontology

 Concepts: Representing entities, objects, or ideas within the domain
 Relationship: Defining how concepts interact, relate, or connect
 Rules: Specifying constraints, Logic, or axioms governing the domain
 Axioms: Fundamental truths or assumptions underlying the ontology
 Instances: specific examples or individuals within the domain.

Benefits of ontology
 Improved knowledge organization and sharing
 Enhanced reasoning & decision-making capabilities.
 Increased data consistency and quality
 Better interoperability and integration
 More explainable and transparent AI Systems

MEMORY ORGANIZATION
 Memory Organization provides a framework within which to understand
the relationship between individual identification, duplicate records, and
the proper functioning of AI
 Types of Memory Organization
There are several types of memory Organization used in computer system.
Memory Organization in Artificial Intelligence can include a variety of
techniques that help AI Systems.

1. E-MDPs: Episodic Memory Organization packets. A network of frames

that contain conceptual information about different types of Episodic
events.
2. Replay memory: A technique used in AI, Particularly in reinforcement
learning, where an agent learns to make decisions by interacting with its
environment.
3. Working memory. Another critical aspect of AI inspired by the human
cognitive System. Memory is central to common sense behavior and also
the basis for learning. Human memory is still not fully understood however
Psycologists have proposed several ideas
4. Short-Term Memory (STM):
 Only a few items at a time can be held here.
 Perceptual information stored directly here
5. Long-Term Memory (ITM):
 Capacity for storage is very large and fairly permanent
 LTM is often divided up further
Episodic Memory: Contains information about Personal experiences
Semantic Memory: General facts with no Personal meaning

Three distinct Memory Organizations Packets (MOPS) code Knowledge

about an sequence
 1st MOP represents the physical sequence of events
 2nd MOP represents the set of social events that takes place
 3rd MDP revolves around the goals of the Person in the particular episode

EXPERT SYSTEM SHELLS

 Expert System shells are a collection of software packages and tools used
to develop expert systems
 A shell provides the developers with Knowledge acquisition, inference
engine, user interface, explanation facility.
 Initially each expert system is build from Scratch (LISP)
 Example of shell is EMYCIN (for Empty- MYCIN derived from MYCIN)
  Expert System shells CUPS, JESS, DROOLS

Expert System has two main parts

 A Knowledge Base: This is where all the expert info is stored
 An inference Engine: This part uses the stored knowledge to figure out
solutions

Benefits of Expert System Shell

 Time and Cost Savings: Less time spent on development means Lower
overall costs
 User - Friendly Interface:
1. Easier Knowledge: input we can add expert knowledge without complex
coding
2. Simple maintenance: Updating the system is straight forward, even for
non-technical users
 flexibility and Customization:
1. Versatile applications: We can use them for different industries like
healthcare, finance or engineering
2. Easy modifications: As your needs change, you can quickly adjust your
expert system

Build in Features
 Inference Engines: It They are already included, so you don't need to build
One from scratch.
 Explanation facilities: These help users understand how the system reaches
its conclusions
  Knowledge base Editors: They make organizing and updating information
simple

>User Interface:
 Easy-to-use screens for inputting data and getting results
 Often includes menus, buttons, forms
 Helps non-technical users interact with the system

>Knowledge Base Editor:

 A tool for adding and organizing expert Knowledge
 Allows, users to input rules, facts and relationships
 Makes it easy to update information as needed

>Explanation Facility:
 Helps users understand how the system reached its decision
 shows the steps and rules used in the reasoning process
 Builds trust by making the system's logic transparent

>Inference Engine:
  The "brain" of the Expert System
 Uses the knowledge base to solve problems or make decision
 Applies logical reasoning to reach conclusions

>Knowledge Acquisition Tools:

 Assist in gathering and structuring expert Knowledge
 May include interview templates or questionnaries
 Helps convert human expertise into a format the system can use

>Rule Builder:
 Allows users to create if then rules easily
 Helps in setting up the logic the system will follow
 often includes a visual interface for creating rules.

Examples of Expert System Shells

>CLIPS (C Language Integrated Production System)
 Developed by NASA
 Free and open-source
 Good for building rule-based expert systems
 Used in space shuttle operations
>Jess (Java Expert System Shell):
 Based on CLIPS but works with Java
 Fast and powerful
 popular in academic and research settings
>Prolog:
 It is not just a shell but is often used to build expert systems
 Good for logical reasoning tasks
 Used in NLP
>Drools:
 Open-source business rules management system.
 Integrates well with Java applications
  Used in many industries for decision automation

Future of Expert System Shells in AI

 The future of ES shells in AI looks bright and full of possibilities. We can
expect to see these tools become more powerful and user-friendly.
 They will likely merge with machine Learning, creating systems that not
only use expert knowledge, but also team and adapt
 As AI continues to evolve, these shells could play a crucial role in
developing. more advanced and flexible systems across Various fields